Systems and methods for transforming a user interface according to predictive models

Abstract

A computerized method for transforming a user interface according to machine learning includes selecting a persona and determining whether a first condition is true for an associated data structure. In response to determining the first condition is true, the method includes determining whether a second condition is true. In response to determining the second condition is not true, the method includes loading a first trained machine learning model, inputting a first set of explanatory variables to generate a first metric, and transforming the user interface according to the first metric. In response to determining the second condition is true, the method includes determining whether a third condition is true. In response to determining the third condition is true, loading a second trained machine learning model, inputting a second set of explanatory variables to generate a second metric, and transforming the user interface according to the second metric.

What is claimed is: 
     
         1 . A computerized method for transforming a user interface according to machine learning, the method comprising:
 selecting a persona from a data store;   loading, into a data processing module, a data structure associated with the selected persona;   determining, at the data processing module, whether a first condition is true for the data structure;   in response to determining the first condition is true for the data structure, determining whether a second condition is true for the data structure;   in response to determining that the second condition is not true for the data structure:
 loading, at the data processing module, a first trained machine learning model, 
 loading, at the data processing module, a first set of explanatory variables from the data structure, 
 inputting, at the data processing module, the first set of explanatory variables to the first trained machine learning model to generate a first metric, and 
 transforming the user interface according to the selected persona and the first metric; 
   in response to determining that the second condition is true for the data structure, determining whether a third condition is true for the data structure; and   in response to determining that the third condition is true for the data structure:
 loading, at the data processing module, a second trained machine learning model, 
 loading, at the data processing module, a second set of explanatory variables from the data structure, 
 inputting, at the data processing module, the second set of explanatory variables to the second trained machine learning model to generate a second metric, and 
 transforming the user interface according to the selected persona and the second metric, 
   wherein the first metric is a probability of the persona transitioning from treatment with a single drug from a first class of drugs to multiple drugs from the first class of drugs within a first epoch.   
     
     
         2 . The method of  claim 1 , wherein the second metric is a probability of the persona transitioning from treatment with a drug not containing a compound to a drug containing the compound within a second epoch. 
     
     
         3 . The method of  claim 2 , wherein the first condition is a presence of at least one drug of the first class of drugs in the data structure. 
     
     
         4 . The method of  claim 3 , wherein the second condition is a presence of more than one drug of the first class of drugs in the data structure. 
     
     
         5 . The method of  claim 4 , wherein the third condition is a presence of the compound in the data structure. 
     
     
         6 . The method of  claim 5 , wherein the first trained machine learning model is a first multiple logistic regression model. 
     
     
         7 . The method of  claim 6 , wherein the second trained machine learning model is a second multiple logistic regression model. 
     
     
         8 . The method of  claim 7 , wherein the first class of drugs comprises drugs associated with treating pulmonary arterial hypertension. 
     
     
         9 . The method of  claim 8 , wherein the compound comprises prostacyclin. 
     
     
         10 . A system for transforming a user interface according to machine learning, comprising:
 a first data store comprising a persona and a data structure associated with the persona;   a second data store comprising:
 at least one of a first trained machine learning model and a second trained machine learning model, and 
 at least one of a first set of explanatory variables and a second set of explanatory variables; and 
   a processor operatively coupled to the first data store and the second data store,   wherein the processor is configured by a set of instructions to:
 determine whether a first condition is true for the data structure, 
 in response to determining the first condition is true for the data structure, determine whether a second condition is true for the data structure, 
 in response to determining the second condition is not true for the data structure:
 input the first set of explanatory variables into the first trained machine learning model and generate a first metric, and 
 transform the user interface according to the first metric, 
 
 in response to determining the second condition is true for the data structure, determine whether a third condition is true for the data structure, and 
 in response to determining the third condition is true for the data structure:
 input the second set of explanatory variables into the second trained machine learning model to generate a second metric, and 
 transform the user interface according to the second metric, and 
 
   wherein the first metric is a probability of the persona transitioning from treatment with a single drug in a first class of drugs to treatment with multiple drugs in the first class of drugs within a first epoch.   
     
     
         11 . The system of  claim 10 , wherein the second metric is a probability of the persona transitioning from treatment with a drug not containing a compound to treatment with a drug containing the compound within a second epoch. 
     
     
         12 . The system of  claim 11 , wherein the first condition is a presence of at least one drug of the first class of drugs in the data structure. 
     
     
         13 . The system of  claim 12 , wherein the second condition is a presence of more than one drug of the first class of drugs in the data structure. 
     
     
         14 . The system of  claim 13 , wherein the second condition is a presence of the compound in the data structure. 
     
     
         15 . The system of  claim 14 , wherein the first trained machine learning model is a first multiple logistic regression model. 
     
     
         16 . The system of  claim 15 , wherein the second trained machine learning model is a second multiple logistic regression model. 
     
     
         17 . The system of  claim 16 , wherein the first class of drugs comprises drugs associated with treating pulmonary arterial hypertension. 
     
     
         18 . The system of  claim 17 , wherein the compound comprises prostacyclin. 
     
     
         19 . A non-transitory computer-readable medium comprising executable instructions for transforming a user interface according to machine learning, wherein the executable instructions include:
 selecting a persona from a data store;   loading, into a data processing module, a data structure associated with a selected persona;   determining, at the data processing module, whether a first condition is true for the data structure;   in response to determining the first condition is true for the data structure, determining whether a second condition is true for the data structure;   in response to determining the second condition is not true for the data structure:
 loading, at the data processing module, a first trained machine learning model, 
 loading, at the data processing module, a first set of explanatory variables from the data structure, 
 inputting, at the data processing module, the first set of explanatory variables to the first trained machine learning model to generate a first metric, and 
 transforming the user interface according to the selected persona and the first metric; 
   in response to determining the second condition is true for the data structure, determining whether a third condition is true for the data structure; and   in response to determining the third condition is true for the data structure:
 loading, at the data processing module, a second trained machine learning model, 
 loading, at the data processing module, a second set of explanatory variables from the data structure, 
 inputting, at the data processing module, the second set of explanatory variables to the second trained machine learning model to generate a second metric, and 
 transforming the user interface according to the selected persona and the second metric, 
   wherein the first metric is a probability of the persona transitioning from treatment with a single drug in a first class of drugs to treatment with multiple drugs in the first class of drugs within a first epoch.   
     
     
         20 . The non-transitory computer-readable medium of  claim 19 , wherein the second metric is a probability of the persona transitioning from treatment with a drug not containing a compound to treatment with a drug containing the compound within a second epoch.